Decision-level Fusion Method Research Articles

OBJECT-ORIENTED CHANGE DETECTION FOR REMOTE SENSING IMAGES BASED ON MULTI-SCALE FUSION

In the process of object-oriented change detection, the determination of the optimal segmentation scale is directly related to the subsequent change information extraction and analysis. Aiming at this problem, this paper presents a novel object-level change detection method based on multi-scale segmentation and fusion. First of all, the fine to coarse segmentation is used to obtain initial objects of different sizes; then, according to the features of the objects, Change Vector Analysis is used to obtain the change detection results of various scales. Furthermore, in order to improve the accuracy of change detection, this paper introduces fuzzy fusion and two kinds of decision level fusion methods to get the results of multi-scale fusion. Based on these methods, experiments are done with SPOT5 multi-spectral remote sensing imagery. Compared with pixel-level change detection methods, the overall accuracy of our method has been improved by nearly 10%, and the experimental results prove the feasibility and effectiveness of the fusion strategies.

OBJECT-ORIENTED CHANGE DETECTION FOR REMOTE SENSING IMAGES BASED ON MULTI-SCALE FUSION

Abstract. In the process of object-oriented change detection, the determination of the optimal segmentation scale is directly related to the subsequent change information extraction and analysis. Aiming at this problem, this paper presents a novel object-level change detection method based on multi-scale segmentation and fusion. First of all, the fine to coarse segmentation is used to obtain initial objects of different sizes; then, according to the features of the objects, Change Vector Analysis is used to obtain the change detection results of various scales. Furthermore, in order to improve the accuracy of change detection, this paper introduces fuzzy fusion and two kinds of decision level fusion methods to get the results of multi-scale fusion. Based on these methods, experiments are done with SPOT5 multi-spectral remote sensing imagery. Compared with pixel-level change detection methods, the overall accuracy of our method has been improved by nearly 10%, and the experimental results prove the feasibility and effectiveness of the fusion strategies.

SROC: A Speaker Recognition with Data Decision Level Fusion Method in Cloud Environment

Speaker recognition as one of biometrics techniques is to recognize speaker's identity. A robust method for speaker recognition with high accuracy of recognition rate is the aim for all relevant researchers. With the rapid development of cloud computing, many complicated tasks in speaker recognition system, such as machine learning, data processing, and information recording, can be implemented in cloud. Meanwhile, speaker recognition can be used as a security and privacy service which are extremely important for the popularization of cloud computing. In this paper, we propose a data decision level fusion method for speaker recognition in cloud environment. After introducing the basic processing of speech recognition process and describing the composition of the speech recognition system based on Dempster-Shafer Evidence Theory of decision level data fusion method, we present a speaker recognition system of cloud computing (SROC) architecture. Through experimental evaluation, SROC can improve the recognition rate and accuracy greatly.

Fusing audio, visual and textual clues for sentiment analysis from multimodal content

A huge number of videos are posted every day on social media platforms such as Facebook and YouTube. This makes the Internet an unlimited source of information. In the coming decades, coping with such information and mining useful knowledge from it will be an increasingly difficult task. In this paper, we propose a novel methodology for multimodal sentiment analysis, which consists in harvesting sentiments from Web videos by demonstrating a model that uses audio, visual and textual modalities as sources of information. We used both feature- and decision-level fusion methods to merge affective information extracted from multiple modalities. A thorough comparison with existing works in this area is carried out throughout the paper, which demonstrates the novelty of our approach. Preliminary comparative experiments with the YouTube dataset show that the proposed multimodal system achieves an accuracy of nearly 80%, outperforming all state-of-the-art systems by more than 20%.

Incorporating social media comments in affective video retrieval

Affective video retrieval systems aim at finding video contents matching the desires and needs of users. Existing systems typically use the information contained in the video itself to specify its affect category. These systems either extract low-level features or build up higher-level attributes to train classification algorithms. However, using low-level features ignores global relations in data and constructing high-level features is time consuming and problem dependent. To overcome these drawbacks, an external source of information may be helpful. With the explosive growth and availability of social media, users’ comments could be such a valuable source of information. In this study, a new method for incorporating social media comments with the audio-visual contents of videos is proposed. Furthermore, for the combination stage a decision-level fusion method based on the Dempster–Shafer theory of evidence is presented. Experiments are carried out on the video clips of the DEAP (Database for Emotion Analysis using Physiological signals) dataset and their associated users’ comments on YouTube. Results show that the proposed system significantly outperforms the baseline method of using only the audio-visual contents for affective video retrieval.

A method for tool condition monitoring based on sensor fusion

This paper presents a multi-sensor information fusion method for tool condition monitoring (TCM) using acoustic emission and cutting sound as monitoring signals. In order to make the cutting state in experiments closer to that in actual production, the traditional data acquisition method was improved. Using time---frequency analysis methods and multi-fractal theories, each kind of signal was filtered and their features were extracted according to characteristics respectively. The decision level fusion method was used for realizing information fusion by the model of support vector machines (SVMs) ensemble. Its base layer composes of two models of SVMs for regression (SVRs). Before training, the two SVRs were optimized by multiple population genetic algorithm including input features selection and model parameters optimization. Its decision layer is a model of SVM for classification or SVR, which is used for the combined decision according to the sub-decisions of SVRs in the base layer. The test results of SVMs ensemble show that the method can be used effectively for classification of tool wear condition and prediction of tool wear quantity. It can make information of the two sensors complement each other and is better than methods using a single sensor for TCM.

A DECISION LEVEL FUSION METHOD FOR OBJECT RECOGNITION USING MULTI-ANGULAR IMAGERY

Abstract. Spectral similarity and spatial adjacency between various kinds of objects, shadow and occluded areas behind high rise objects as well as complex relationships lead to object recognition difficulties and ambiguities in complex urban areas. Using new multi-angular satellite imagery, higher levels of analysis and developing a context aware system may improve object recognition results in these situations. In this paper, the capability of multi-angular satellite imagery is used in order to solve object recognition difficulties in complex urban areas based on decision level fusion of Object Based Image Analysis (OBIA). The proposed methodology has two main stages. In the first stage, object based image analysis is performed independently on each of the multi-angular images. Then, in the second stage, the initial classified regions of each individual multi-angular image are fused through a decision level fusion based on the definition of scene context. Evaluation of the capabilities of the proposed methodology is performed on multi-angular WorldView-2 satellite imagery over Rio de Janeiro (Brazil).The obtained results represent several advantages of multi-angular imagery with respect to a single shot dataset. Together with the capabilities of the proposed decision level fusion method, most of the object recognition difficulties and ambiguities are decreased and the overall accuracy and the kappa values are improved.

Discriminative fusion of shape and appearance features for human pose estimation

This paper presents a method for combining the shape and appearance feature types in a discriminative learning framework for human pose estimation. We first present a new appearance descriptor that is distinctive and resilient to noise for 3D human pose estimation. We then combine the proposed appearance descriptor with a shape descriptor computed from the silhouette of the human subject using discriminative learning. Our method, which we refer to as a localized decision level fusion technique, is based on clustering the output pose space into several partitions and learning a decision level fusion model for the shape and appearance descriptors in each region. The combined shape and appearance descriptor allows complementary information of the individual feature types to be exploited, leading to improved performance of the pose estimation system. We evaluate our proposed fusion method with feature level fusion and kernel level fusion methods using a synchronized video and 3D motion dataset. Our experimental results show that the proposed feature combination method gives more accurate pose estimation than the one obtained from each individual feature type. Among the three fusion methods, our localized decision level fusion method is demonstrated to perform the best for 3D pose estimation.

Multi-modal tracking of people using laser scanners and video camera

Inspite extensive research on visual tracking of multiple people in computer vision area, the robustness and usability of visual trackers are still discouraging. Recently, a few laser-based detection and tracking methods have been developed in robotics area. However, poor features provided by laser data make the tracker fail in many situations. In this paper, we present a novel method that aims at reliably detecting and tracking multiple people in an open area. Multiple laser scanners and one camera are used as input sensors. In detection stage, laser-based detection algorithm captures newly appeared people and initializes the mean-shift-based visual tracker. In tracking stage, laser-based feet trajectory tracking result and visual body region tracking result are combined with a decision-level Bayesian fusion method. The experimental results demonstrate reliable and real-time performance of the method.

Iris recognition based on score level fusion by using SVM

In conventional iris recognition methods, due to the difficulty of selecting one optimal wavelet filter for iris feature extraction, multiple wavelet filters (with different frequencies and kernel sizes) are adopted. However, this causes the processing time and the extracted feature size to increase. To overcome this problem, feature level fusion of the extracted iris features has been proposed, but this method requires a complicated dimension reduction procedure. Therefore, we propose a new iris recognition method based on score level fusion, using two Gabor wavelet filters and SVM (support vector machine). For score level fusion, we used the typical HD (Hamming distance) produced by a Gabor filter, which can easily be applied to conventional iris recognition systems. The proposed method has three novelties compared to previous works. First, when generating iris feature codes, we excluded detected eyelid, eyelash and SR (specular reflection) regions, which act as noise factors in iris feature extraction. Second, for enrollment, we checked the number of reliable iris feature codes that were not generated from the eyelid, eyelash and SR occluded regions. Only if the number of reliable codes exceeded in the predetermined threshold, we performed enrollment with high confidence, which reduced the FRR (false rejection rate). Third, two Gabor filters were used for local and global iris textures and the HDs calculated by those Gabor filters were fused by the SVM and the consequent authentication error was greatly reduced. Experimental results showed that the authentication error of the proposed method was much smaller than the authentication errors when using the single Gabor filter, the filter-bank, the score level and the decision level fusion methods.